agentleFS
Sign inStart free
lynchypinlynchypin/project-onboard/skills/document-directory/SKILL.md

document-directory

Skill0 starsChanged 3 months agoMITView on GitHub

Create or update a subdirectory's own CLAUDE.md file after substantial work in that module. Only for app or system documentation tier projects.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After implementation has touched a module substantially enough that a future session would benefit from a summary.

    line 15
  2. Distinctive:

    Check for existing subdirectory CLAUDE.md: If one exists, update it with what's new — preserve prior content that's still accurate.

    line 20
  3. Distinctive:

    Do not repeat root CLAUDE.md content — inheritance is automatic.

    line 29
  4. Distinctive:

    Never run on script or tool tier projects.

    line 40
  5. Distinctive:

    Never duplicate root CLAUDE.md content.

    line 41
  6. Distinctive:

    Never let a subdirectory file grow to root-file length.

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Document directory

Claude Code loads subdirectory CLAUDE.md files on demand, only when it reads a file in that subtree. Detailed knowledge sits exactly where it's relevant without bloating every session.

When to run

  • Doc tier is app or system. Never for script or tool.
  • After implementation has touched a module substantially enough that a future session would benefit from a summary.

Process

  1. Check for existing subdirectory CLAUDE.md. If one exists, update it with what's new — preserve prior content that's still accurate.
  2. If none exists, create one covering:
    • Purpose and responsibility (1-2 sentences).
    • Key architectural decisions (link to ADRs where they exist).
    • Non-obvious patterns or gotchas a future session would have to rediscover.
    • Do not repeat root CLAUDE.md content — inheritance is automatic.
  3. Keep it short. A subdirectory CLAUDE.md as long as the root file has lost the point. Complex modules get an ADR or dedicated doc linked from a still-short CLAUDE.md.
  4. Commit separately from implementation unless the project's convention says otherwise.

What this skill must never do

  • Never run on script or tool tier projects.
  • Never duplicate root CLAUDE.md content.
  • Never let a subdirectory file grow to root-file length.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free